Automatic language recognition

Abstract

Techniques for automatic language recognition are provided. A device having an interfaced microphone detects conversations occurring in proximity to the device. The conversations are resolved to a specific spoken language. Information communicated from or on the device is then updated to be consistent with the spoken language. This language transition for the device is achieved automatically and without any affirmative action on the part of a user or administrator associated with the device.

The invention claimed is: 
     
       1. A processor-implemented method programmed in memory and/or
 a non-transitory processor-readable medium and to execute on one or more processors of 
 a device configured to execute the method, comprising: 
 detecting, on the device, audio in proximity to a microphone, wherein detecting further includes detecting the audio as speech from one of: a single person conversing on a phone in proximity to the microphone and multiple people conversing with one another in proximity to the microphone; 
 filtering, on the device, the audio to detect speech; and 
 translating, on the device, information originally being presented on a digital display in an original written language into a target written language identified for a spoken language and resolved for the detected speech, wherein the information is presented on the digital display in the target written language replacing the information presented on the digital display in the original written language, and modifying an original image presented on the digital display with a new image that is appropriate for a cultural of the spoken language. 
 
     
     
       2. The method of  claim 1  further comprising, operating, on the device, the method within a kiosk. 
     
     
       3. The method of  claim 1  further comprising, operating, on the device, the method within a digital sign. 
     
     
       4. The method of  claim 1  further comprising, updating, via the device, the digital display to be consistent with cultural norms associated with the resolved spoken language. 
     
     
       5. The method of  claim 1 , wherein filtering further includes controlling a decibel level from the detected audio. 
     
     
       6. The method of  claim 5 , wherein controlling further includes removing noise identified in the detected audio. 
     
     
       7. The method of  claim 1 , wherein translating further includes consulting a speech resolution service with a snippet of the filtered audio to resolve the spoken language. 
     
     
       8. The method of  claim 1 , wherein translating further includes identifying a potential list of candidate languages for the spoken language based on analysis and permitting a user to select the spoken language on the digital display. 
     
     
       9. A processor-implemented method programmed in memory and/or a non-transitory processor-readable medium and to execute on one or more processors of a device configured to execute the method, comprising:
 collecting, via the device, sample audio snippets from an environment in proximity to the device, wherein collecting further includes collecting the audio snippets from one of: a single person conversing on a phone in proximity to the device and multiple people conversing with one another in proximity to the device; 
 resolving, on the device, a predominately spoken language being spoken in the sample audio snippets; and 
 updating, on the device, communications associated with the device to the spoken language by providing the updated communications as written communication and information in the spoken language and translating original written communications presented on a display of the device into the written communication and the information for the spoken language on the display of the device, and modifying an original image presented on the display with a new image that is appropriate for a cultural of the spoken language. 
 
     
     
       10. The method of  claim 9 , wherein collecting further includes operating the device as one or more of a digital sign, a kiosk, and a robot. 
     
     
       11. The method of  claim 9 , wherein collecting further includes changing written language information to a specific written language associated with the spoken language. 
     
     
       12. The method of  claim 9 , wherein updating further includes dynamically configuring audio communications and speech recognition for the device to the spoken language. 
     
     
       13. A system, comprising:
 a digital display; 
 a microphone integrated within or interfaced to the digital display; and 
 memory having a language translator that processes as executable instructions on one or more processors of the digital display; 
 wherein the language translator is configured to detect voice conversations in proximity to the microphone and resolve a spoken language for the voice conversations and in response thereto translating original written information presented on the digital display in an original language to a target language for the spoken language and presenting the written information and written communication in the target language on the digital display, wherein the voice conversations are obtained from one of: a single person conversing on a phone in proximity to the microphone and multiple people conversing with one another in proximity to the microphone, and wherein the language translator is further configured to modify an original image presented on the digital display with a new image that is appropriate for a cultural of the spoken language. 
 
     
     
       14. The system of  claim 13 , wherein the system is a kiosk. 
     
     
       15. The system of  claim 13 , wherein the system is a digital sign. 
     
     
       16. The system of  claim 13 , wherein the language translator is configured to filter noise from the voice conversations to improve accuracy associated with resolving the spoken language. 
     
     
       17. The system of  claim 13 , wherein the language translator is configured to consult a remote third-party service with an audio snippet from the voice conversations to resolve the spoken language. 
     
     
       18. The system of  claim 13 , wherein the language translator is configured to present a predefined list of languages on the digital display to permit a user interacting with the digital display as a kiosk to select the spoken language, the predefined list narrowed by the language translator by analyzing the voice conversations. 
     
     
       19. The system of  claim 13 , wherein the language translator is configured with a decibel control mechanism to adjust a decibel level for the voice conversations when resolving the spoken language. 
     
     
       20. The system of  claim 13 , wherein the language translator is configured to alter non-language information presented on the digital display based on cultural norms associated with the resolved spoken language.